import numpy as np import json img_codes = np.load("data/image_codes.npy") captions = json.load(open('data/captions_tokenized.json')) for img_i in range(len(captions)): for caption_i inrange(len(captions[img_i])): sentence = captions[img_i][caption_i] captions[img_i][caption_i] = ["#START#"] + sentence.split(' ') + ["#END#"]   class CaptionNet(nn.Module):   def__init__(self, n_tokens=n_tokens, emb_size=128, lstm_units=256, cnn_feature_size=2048): """ A recurrent 'head' network for image captioning. See scheme above. """ super().__init__()   # a layer that converts conv features to initial_h (h_0) and initial_c (c_0) self.cnn_to_h0 = nn.Linear(cnn_feature_size, lstm_units) self.cnn_to_c0 = nn.Linear(cnn_feature_size, lstm_units) # create embedding for input words. Use the parameters (e.g. emb_size). # YOUR CODE HERE   # lstm: create a recurrent core of your network. Use either LSTMCell or just LSTM. # In the latter case (nn.LSTM), make sure batch_first=True # YOUR CODE HERE   # create logits: linear layer that takes lstm hidden state as input and computes one number per token # YOUR CODE HERE   defforward(self, image_vectors, captions_ix): """ Apply the network in training mode. :param image_vectors: torch tensor containing inception vectors. shape: [batch, cnn_feature_size] :param captions_ix: torch tensor containing captions as matrix. shape: [batch, word_i]. padded with pad_ix :returns: logits for next token at each tick, shape: [batch, word_i, n_tokens] """ self.lstm.flatten_parameters() initial_cell = self.cnn_to_c0(image_vectors) initial_hid = self.cnn_to_h0(image_vectors)   # compute embeddings for captions_ix # YOUR CODE HERE   # apply recurrent layer to captions_emb. # 1. initialize lstm state with initial_* from above # 2. feed it with captions. Mind the dimension order in docstring # 3. compute logits for next token probabilities # Note: if you used nn.LSTM, you can just give it (initial_cell[None], initial_hid[None]) as second arg # lstm_out should be lstm hidden state sequence of shape [batch, caption_length, lstm_units] # YOUR CODE HERE   # compute logits from lstm_out # YOUR CODE HERE #for reference and more detail go to ---> https://colab.research.google.com/github/hse-aml/intro-to-dl-pytorch/blob/main/week06/week06_final_project_image_captioning.ipynb#scrollTo=x_wH1bYu-QK8

Clear Explanation on this question add some step to leading on how you answerd it neat handwriting and clear explanation table completed Question are below here:

Here is my entire code(average is not working yet). The response I got from the professor is that I have to create a DRY solution replacing the five display_functions with a single get_array function you call five times like common_array = get_array(plant_xml, "COMMON") etc.    from urllib.request import urlopenfrom xml.etree.ElementTree import parse def read_data(data_file):    plant_url = urlopen(data_file)    plant_xml = parse(plant_url)    return plant_xml def display_common_items(plant_xml):    plant_root = plant_xml.getroot()    common_array = []    for item in plant_root.findall("PLANT"):        common_array.append(item.find("COMMON").text)    return common_array def display_botanical_items(plant_xml):    plant_root = plant_xml.getroot()    botanical_array = []    for item in plant_root.findall("PLANT"):        botanical_array.append(item.find("BOTANICAL").text)    return botanical_array def display_zone_items(plant_xml):    plant_root = plant_xml.getroot()    zone_array = []…

Determine if the following statement are true or false screen shot shows the text's SortedArrayCollection and ArrayCollection When comparing two objects using the == operator, what is actually compared is the references to the objects. When comparing two objects using the equals method inherited from the Object class, what is actually compared is the references to the objects. The text's sorted array-based collection implementation stores elements in the lowest possible indices of the array. The text's array-based collection implementation stores elements in the lowest possible indices of the array.